Investigation on Data Adaptation Techniques for Neural Named Entity Recognition

• URL: http://arxiv.org/abs/2110.05892v1
• Date: Tue, 12 Oct 2021 11:06:03 GMT
• Title: Investigation on Data Adaptation Techniques for Neural Named Entity Recognition
• Authors: Evgeniia Tokarchuk, David Thulke, Weiyue Wang, Christian Dugast, Hermann Ney
• Abstract summary: A common practice is to utilize large monolingual unlabeled corpora. Another popular technique is to create synthetic data from the original labeled data. In this work, we investigate the impact of these two methods on the performance of three different named entity recognition tasks.
• Score: 51.88382864759973
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Data processing is an important step in various natural language processing tasks. As the commonly used datasets in named entity recognition contain only a limited number of samples, it is important to obtain additional labeled data in an efficient and reliable manner. A common practice is to utilize large monolingual unlabeled corpora. Another popular technique is to create synthetic data from the original labeled data (data augmentation). In this work, we investigate the impact of these two methods on the performance of three different named entity recognition tasks.

Related papers

• Maximizing Data Efficiency for Cross-Lingual TTS Adaptation by Self-Supervised Representation Mixing and Embedding Initialization [57.38123229553157]
  This paper presents an effective transfer learning framework for language adaptation in text-to-speech systems. We focus on achieving language adaptation using minimal labeled and unlabeled data. Experimental results show that our framework is able to synthesize intelligible speech in unseen languages with only 4 utterances of labeled data and 15 minutes of unlabeled data.
  arXiv  Detail & Related papers  (2024-01-23T21:55:34Z)
• Disambiguation of Company names via Deep Recurrent Networks [101.90357454833845]
  We propose a Siamese LSTM Network approach to extract -- via supervised learning -- an embedding of company name strings. We analyse how an Active Learning approach to prioritise the samples to be labelled leads to a more efficient overall learning pipeline.
  arXiv  Detail & Related papers  (2023-03-07T15:07:57Z)
• Using Domain Knowledge for Low Resource Named Entity Recognition [2.749726993052939]
  We propose to use domain knowledge to improve the performance of named entity recognition in areas with low resources. The proposed model avoids large-scale data adjustments in different domains while handling named entities recognition with low resources.
  arXiv  Detail & Related papers  (2022-03-28T13:26:47Z)
• Hierarchical Transformer Model for Scientific Named Entity Recognition [0.20646127669654832]
  We present a simple and effective approach for Named Entity Recognition. The main idea of our approach is to encode the input subword sequence with a pre-trained transformer such as BERT. We evaluate our approach on three benchmark datasets for scientific NER.
  arXiv  Detail & Related papers  (2022-03-28T12:59:06Z)
• An Analysis of Simple Data Augmentation for Named Entity Recognition [21.013836715832564]
  We design and compare data augmentation for named entity recognition. We show that simple augmentation can boost performance for both recurrent and transformer-based models.
  arXiv  Detail & Related papers  (2020-10-22T13:21:03Z)
• Adaptive Self-training for Few-shot Neural Sequence Labeling [55.43109437200101]
  We develop techniques to address the label scarcity challenge for neural sequence labeling models. Self-training serves as an effective mechanism to learn from large amounts of unlabeled data. meta-learning helps in adaptive sample re-weighting to mitigate error propagation from noisy pseudo-labels.
  arXiv  Detail & Related papers  (2020-10-07T22:29:05Z)
• Adversarial Knowledge Transfer from Unlabeled Data [62.97253639100014]
  We present a novel Adversarial Knowledge Transfer framework for transferring knowledge from internet-scale unlabeled data to improve the performance of a classifier. An important novel aspect of our method is that the unlabeled source data can be of different classes from those of the labeled target data, and there is no need to define a separate pretext task.
  arXiv  Detail & Related papers  (2020-08-13T08:04:27Z)
• Omni-supervised Facial Expression Recognition via Distilled Data [120.11782405714234]
  We propose omni-supervised learning to exploit reliable samples in a large amount of unlabeled data for network training. We experimentally verify that the new dataset can significantly improve the ability of the learned FER model. To tackle this, we propose to apply a dataset distillation strategy to compress the created dataset into several informative class-wise images.
  arXiv  Detail & Related papers  (2020-05-18T09:36:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.